user/dev discussion of public-inbox itself
 help / color / mirror / code / Atom feed
Search results ordered by [date|relevance]  view[summary|nested|Atom feed]
thread overview below | download mbox.gz: |
* [PATCH 1/5] lei: reinstate JSON smsg output deduplication
  @ 2021-01-25  1:18  4% ` Eric Wong
  0 siblings, 0 replies; 4+ results
From: Eric Wong @ 2021-01-25  1:18 UTC (permalink / raw)
  To: meta

This was accidentally clobbered completely in
("lei q: fix JSON overview with remote externals").
There are now more tests to prevent future regressions.
---
 lib/PublicInbox/LeiOverview.pm |  7 ++++++-
 t/lei.t                        | 19 ++++++++++++++++---
 2 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/lib/PublicInbox/LeiOverview.pm b/lib/PublicInbox/LeiOverview.pm
index 928d66cb..880c7acc 100644
--- a/lib/PublicInbox/LeiOverview.pm
+++ b/lib/PublicInbox/LeiOverview.pm
@@ -203,12 +203,14 @@ sub ovv_each_smsg_cb { # runs in wq worker usually
 	my ($self, $lei, $ibxish) = @_;
 	my $json;
 	$lei->{1}->autoflush(1);
+	my $dedupe = $lei->{dedupe} // die 'BUG: {dedupe} missing';
 	if (my $pkg = $self->{json}) {
 		$json = $pkg->new;
 		$json->utf8->canonical;
 		$json->ascii(1) if $lei->{opt}->{ascii};
+		$lei->{ovv_buf} = \(my $buf = '');
 	}
-	my $l2m = $lei->{l2m};
+	my $l2m = $lei->{l2m} or $dedupe->prepare_dedupe;
 	if ($l2m && !$ibxish) { # remote https?:// mboxrd
 		delete $l2m->{-wq_s1};
 		my $g2m = $l2m->can('git_to_mail');
@@ -241,6 +243,7 @@ sub ovv_each_smsg_cb { # runs in wq worker usually
 		my $git = $ibxish->git; # (LeiXSearch|Inbox|ExtSearch)->git
 		$self->{git} = $git; # for ovv_atexit_child
 		my $g2m = $l2m->can('git_to_mail');
+		$dedupe->prepare_dedupe;
 		sub {
 			my ($smsg, $mitem) = @_;
 			$smsg->{pct} = get_pct($mitem) if $mitem;
@@ -251,6 +254,7 @@ sub ovv_each_smsg_cb { # runs in wq worker usually
 		$lei->{ovv_buf} = \(my $buf = '');
 		sub { # DIY prettiness :P
 			my ($smsg, $mitem) = @_;
+			return if $dedupe->is_smsg_dup($smsg);
 			$smsg = _unbless_smsg($smsg, $mitem);
 			$buf .= "{\n";
 			$buf .= join(",\n", map {
@@ -274,6 +278,7 @@ sub ovv_each_smsg_cb { # runs in wq worker usually
 		$lei->{ovv_buf} = \(my $buf = '');
 		sub {
 			my ($smsg, $mitem) = @_;
+			return if $dedupe->is_smsg_dup($smsg);
 			$buf .= $json->encode(_unbless_smsg(@_)) . $ORS;
 			if (length($buf) > 65536) {
 				my $lk = $self->lock_for_scope;
diff --git a/t/lei.t b/t/lei.t
index 3fd1d1fe..f826a966 100644
--- a/t/lei.t
+++ b/t/lei.t
@@ -17,6 +17,7 @@ my $err_filter;
 my @onions = qw(http://hjrcffqmbrq6wope.onion/meta/
 	http://czquwvybam4bgbro.onion/meta/
 	http://ou63pmih66umazou.onion/meta/);
+my $json = ref(PublicInbox::Config->json)->new->utf8->canonical;
 my $lei = sub {
 	my ($cmd, $env, $xopt) = @_;
 	$out = $err = '';
@@ -142,8 +143,7 @@ my $setup_publicinboxes = sub {
 		my ($ibx) = @_;
 		my $im = PublicInbox::InboxWritable->new($ibx)->importer(0);
 		my $V = $ibx->version;
-		my @eml = glob('t/*.eml');
-		push(@eml, 't/data/0001.patch') if $V == 2;
+		my @eml = (glob('t/*.eml'), 't/data/0001.patch');
 		for (@eml) {
 			next if $_ eq 't/psgi_v2-old.eml'; # dup mid
 			$im->add(eml_load($_)) or BAIL_OUT "v$V add $_";
@@ -176,7 +176,7 @@ SKIP: {
 	my $mid = '20140421094015.GA8962@dcvr.yhbt.net';
 	ok($lei->('q', "m:$mid"), "query $url");
 	is($err, '', "no errors on $url");
-	my $res = PublicInbox::Config->json->decode($out);
+	my $res = $json->decode($out);
 	is($res->[0]->{'m'}, "<$mid>", "got expected mid from $url");
 	ok($lei->('q', "m:$mid", 'd:..20101002'), 'no results, no error');
 	like($err, qr/404/, 'noted 404');
@@ -246,6 +246,19 @@ my $test_external = sub {
 	# No double-quoting should be imposed on users on the CLI
 	$lei->('q', 's:use boolean prefix');
 	like($out, qr/search: use boolean prefix/, 'phrase search got result');
+	my $res = $json->decode($out);
+	is(scalar(@$res), 2, 'only 2 element array (1 result)');
+	is($res->[1], undef, 'final element is undef'); # XXX should this be?
+	is(ref($res->[0]), 'HASH', 'first element is hashref');
+	$lei->('q', '--pretty', 's:use boolean prefix');
+	my $pretty = $json->decode($out);
+	is_deeply($res, $pretty, '--pretty is identical after decode');
+
+	for my $fmt (qw(ldjson ndjson jsonl)) {
+		$lei->('q', '-f', $fmt, 's:use boolean prefix');
+		is($out, $json->encode($pretty->[0])."\n", "-f $fmt");
+	}
+
 	require IO::Uncompress::Gunzip;
 	for my $sfx ('', '.gz') {
 		my $f = "$home/mbox$sfx";

^ permalink raw reply related	[relevance 4%]

* Re: [PATCH 7/9] lei q: fix JSON overview with remote externals
  2021-01-24 11:46  5% ` [PATCH 7/9] lei q: fix JSON overview with remote externals Eric Wong
@ 2021-01-24 12:37  7%   ` Eric Wong
  0 siblings, 0 replies; 4+ results
From: Eric Wong @ 2021-01-24 12:37 UTC (permalink / raw)
  To: meta

Eric Wong <e@80x24.org> wrote:
> --- a/lib/PublicInbox/LeiOverview.pm
> +++ b/lib/PublicInbox/LeiOverview.pm
> @@ -209,7 +209,7 @@ sub ovv_each_smsg_cb { # runs in wq worker usually
>  		$json->ascii(1) if $lei->{opt}->{ascii};
>  	}
>  	my $l2m = $lei->{l2m};
> -	if ($l2m && $ibxish->can('scheme')) { # remote https?:// mboxrd
> +	if ($l2m && !$ibxish) { # remote https?:// mboxrd

I made this change last, thus necessitating changes to callers:

> --- a/lib/PublicInbox/LeiXSearch.pm
> +++ b/lib/PublicInbox/LeiXSearch.pm

> @@ -208,9 +201,9 @@ sub query_remote_mboxrd {
>  	}
>  	$opt->{torsocks} = 'false' if $opt->{'no-torsocks'};
>  	my $tor = $opt->{torsocks} //= 'auto';
> +	my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei, $uris->[0]);

Will squash this in, otherwise --remote --no-local won't work:

diff --git a/lib/PublicInbox/LeiXSearch.pm b/lib/PublicInbox/LeiXSearch.pm
index 841257c1..fb608d00 100644
--- a/lib/PublicInbox/LeiXSearch.pm
+++ b/lib/PublicInbox/LeiXSearch.pm
@@ -201,7 +201,7 @@ sub query_remote_mboxrd {
 	}
 	$opt->{torsocks} = 'false' if $opt->{'no-torsocks'};
 	my $tor = $opt->{torsocks} //= 'auto';
-	my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei, $uris->[0]);
+	my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei);
 	for my $uri (@$uris) {
 		$uri->query_form(@qform);
 		my $cmd = [ @cmd, $uri->as_string ];

^ permalink raw reply related	[relevance 7%]

* [PATCH 7/9] lei q: fix JSON overview with remote externals
  2021-01-24 11:46  6% [PATCH 0/9] lei remotes fixes and updates Eric Wong
@ 2021-01-24 11:46  5% ` Eric Wong
  2021-01-24 12:37  7%   ` Eric Wong
  0 siblings, 1 reply; 4+ results
From: Eric Wong @ 2021-01-24 11:46 UTC (permalink / raw)
  To: meta

We can't (and don't need to) repeatedly get the $each_smsg
callback for each URI since that clobbers {ovv_buf} before
it can be output.

I initially thought this was a dedupe-related bug and
moved the dedupe code into the $each_smsg callback to
minimize differences.  Nevertheless it's a nice code
reduction.

I also thought it was related to incomplete smsg info,
so {references} is now filled in correctly for dedupe.
---
 lib/PublicInbox/LeiOverview.pm |  2 +-
 lib/PublicInbox/LeiXSearch.pm  | 15 +++++----------
 2 files changed, 6 insertions(+), 11 deletions(-)

diff --git a/lib/PublicInbox/LeiOverview.pm b/lib/PublicInbox/LeiOverview.pm
index 49538a60..928d66cb 100644
--- a/lib/PublicInbox/LeiOverview.pm
+++ b/lib/PublicInbox/LeiOverview.pm
@@ -209,7 +209,7 @@ sub ovv_each_smsg_cb { # runs in wq worker usually
 		$json->ascii(1) if $lei->{opt}->{ascii};
 	}
 	my $l2m = $lei->{l2m};
-	if ($l2m && $ibxish->can('scheme')) { # remote https?:// mboxrd
+	if ($l2m && !$ibxish) { # remote https?:// mboxrd
 		delete $l2m->{-wq_s1};
 		my $g2m = $l2m->can('git_to_mail');
 		my $wcb = $l2m->write_cb($lei);
diff --git a/lib/PublicInbox/LeiXSearch.pm b/lib/PublicInbox/LeiXSearch.pm
index c6ff5679..2bedf000 100644
--- a/lib/PublicInbox/LeiXSearch.pm
+++ b/lib/PublicInbox/LeiXSearch.pm
@@ -15,6 +15,7 @@ use File::Temp 0.19 (); # 0.19 for ->newdir
 use File::Spec ();
 use PublicInbox::Search qw(xap_terms);
 use PublicInbox::Spawn qw(popen_rd);
+use PublicInbox::MID qw(mids);
 
 sub new {
 	my ($class) = @_;
@@ -120,8 +121,6 @@ sub query_thread_mset { # for --thread
 	my $mo = { %{$lei->{mset_opt}} };
 	my $mset;
 	my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei, $ibxish);
-	my $dedupe = $lei->{dedupe} // die 'BUG: {dedupe} missing';
-	$dedupe->prepare_dedupe;
 	do {
 		$mset = $srch->mset($mo->{qstr}, $mo);
 		my $ids = $srch->mset_to_artnums($mset, $mo);
@@ -132,7 +131,6 @@ sub query_thread_mset { # for --thread
 			for my $n (@{$ctx->{xids}}) {
 				my $smsg = $over->get_art($n) or next;
 				wait_startq($startq) if $startq;
-				next if $dedupe->is_smsg_dup($smsg);
 				my $mitem = delete $n2item{$smsg->{num}};
 				$each_smsg->($smsg, $mitem);
 			}
@@ -155,14 +153,11 @@ sub query_mset { # non-parallel for non-"--thread" users
 		attach_external($self, $loc);
 	}
 	my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei, $self);
-	my $dedupe = $lei->{dedupe} // die 'BUG: {dedupe} missing';
-	$dedupe->prepare_dedupe;
 	do {
 		$mset = $self->mset($mo->{qstr}, $mo);
 		for my $mitem ($mset->items) {
 			my $smsg = smsg_for($self, $mitem) or next;
 			wait_startq($startq) if $startq;
-			next if $dedupe->is_smsg_dup($smsg);
 			$each_smsg->($smsg, $mitem);
 		}
 	} while (_mset_more($mset, $mo));
@@ -174,10 +169,10 @@ sub each_eml { # callback for MboxReader->mboxrd
 	my ($eml, $self, $lei, $each_smsg) = @_;
 	my $smsg = bless {}, 'PublicInbox::Smsg';
 	$smsg->populate($eml);
+	PublicInbox::OverIdx::parse_references($smsg, $eml, mids($eml));
 	$smsg->{$_} //= '' for qw(from to cc ds subject references mid);
 	delete @$smsg{qw(From Subject -ds -ts)};
 	if (my $startq = delete($self->{5})) { wait_startq($startq) }
-	return if !$lei->{l2m} && $lei->{dedupe}->is_smsg_dup($smsg);
 	$each_smsg->($smsg, undef, $eml);
 }
 
@@ -189,8 +184,6 @@ sub query_remote_mboxrd {
 	my ($opt, $env) = @$lei{qw(opt env)};
 	my @qform = (q => $lei->{mset_opt}->{qstr}, x => 'm');
 	push(@qform, t => 1) if $opt->{thread};
-	my $dedupe = $lei->{dedupe} // die 'BUG: {dedupe} missing';
-	$dedupe->prepare_dedupe;
 	my @cmd = (qw(curl -sSf -d), '');
 	my $verbose = $opt->{verbose};
 	push @cmd, '-v' if $verbose;
@@ -208,9 +201,9 @@ sub query_remote_mboxrd {
 	}
 	$opt->{torsocks} = 'false' if $opt->{'no-torsocks'};
 	my $tor = $opt->{torsocks} //= 'auto';
+	my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei, $uris->[0]);
 	for my $uri (@$uris) {
 		$uri->query_form(@qform);
-		my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei, $uri);
 		my $cmd = [ @cmd, $uri->as_string ];
 		if ($tor eq 'auto' && substr($uri->host, -6) eq '.onion' &&
 				(($env->{LD_PRELOAD}//'') !~ /torsocks/)) {
@@ -236,6 +229,7 @@ sub query_remote_mboxrd {
 			$lei->child_error($?);
 		}
 	}
+	undef $each_smsg;
 	$lei->{ovv}->ovv_atexit_child($lei);
 }
 
@@ -387,6 +381,7 @@ sub ipc_atfork_prepare {
 	my ($self) = @_;
 	if (exists $self->{remotes}) {
 		require PublicInbox::MboxReader;
+		require PublicInbox::OverIdx; # parse_references
 		require IO::Uncompress::Gunzip;
 	}
 	# FDS: (0: done_wr, 1: stdout|mbox, 2: stderr,

^ permalink raw reply related	[relevance 5%]

* [PATCH 0/9] lei remotes fixes and updates
@ 2021-01-24 11:46  6% Eric Wong
  2021-01-24 11:46  5% ` [PATCH 7/9] lei q: fix JSON overview with remote externals Eric Wong
  0 siblings, 1 reply; 4+ results
From: Eric Wong @ 2021-01-24 11:46 UTC (permalink / raw)
  To: meta

Eric Wong (9):
  lei q: limit concurrency to 4 remote connections
  ipc: wq supports arbitrarily large payloads
  ipc: get rid of wq_set_recv_modes
  lei q: disable remote externals if locals exist
  lei q: honor --no-local to force remote searches
  lei_xsearch: use curl -d '' for nginx compatibility
  lei q: fix JSON overview with remote externals
  smsg: make parse_references an object method
  smsg: parse_references: micro-optimization to avoid ++

 lib/PublicInbox/IPC.pm         |  85 +++++++++++++++++----------
 lib/PublicInbox/LEI.pm         |   9 ++-
 lib/PublicInbox/LeiOverview.pm |   2 +-
 lib/PublicInbox/LeiQuery.pm    |  13 ++++-
 lib/PublicInbox/LeiToMail.pm   |   7 +--
 lib/PublicInbox/LeiXSearch.pm  | 101 ++++++++++++++++++---------------
 lib/PublicInbox/OverIdx.pm     |  22 +------
 lib/PublicInbox/SearchIdx.pm   |   2 +-
 lib/PublicInbox/Smsg.pm        |  22 ++++++-
 script/lei                     |  11 ++--
 t/cmd_ipc.t                    |  16 ++++++
 t/ipc.t                        |  21 ++++++-
 t/lei.t                        |   3 +
 13 files changed, 196 insertions(+), 118 deletions(-)


^ permalink raw reply	[relevance 6%]

Results 1-4 of 4 | reverse | sort options + mbox downloads above
-- links below jump to the message on this page --
2021-01-24 11:46  6% [PATCH 0/9] lei remotes fixes and updates Eric Wong
2021-01-24 11:46  5% ` [PATCH 7/9] lei q: fix JSON overview with remote externals Eric Wong
2021-01-24 12:37  7%   ` Eric Wong
2021-01-25  1:18     [PATCH 0/5] lei: more fixes and usability enhancement Eric Wong
2021-01-25  1:18  4% ` [PATCH 1/5] lei: reinstate JSON smsg output deduplication Eric Wong

Code repositories for project(s) associated with this public inbox

	https://80x24.org/public-inbox.git

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).